The paper investigates whether lower stereotype bias scores in multilingual language models truly indicate greater fairness. By auditing ten open models across eight languages, the authors show that lower average scores often arise from translation artifacts rather than genuine bias reduction, as item‑level correlations between English and translated scores are weak. They also identify pipeline errors that can mask bias signals and provide code to replicate their findings.
By Harsh Kumar
arXiv:2605.12515v3 Announce Type: replace
Abstract: Multilingual large language models (MLLMs) often answer culturally ambiguous questions inconsistently across languages, even for a fixed user perso...
By Lucas Resck, Isabelle Augenstein, Anna Korhonen
arXiv:2609.08515v1 Announce Type: cross
Abstract: As Large Language Models (LLMs) are increasingly integrated into human society, aligning them with pluralistic social values has become a critical pr...
By Yuemei Xu, Kexin Xu, Jian Zhou, Haoyu Lu, Yequan Wang, Aishan Liu
Large language models (LLMs) are used worldwide, yet disproportionately reflect Western values, limiting their ability to represent diverse value systems. We introduce PLURAL, a large-scale, value-focused preference dataset grounded in the Integrated Values Survey (IVS), a nationally representative survey spanning 92 countries.
arXiv:2610.35168v1 Announce Type: new
Abstract: The value of language models for any community depends on whether a model actually understands the culture of the people it intends to serve. We use th...
By Blessing Ngozi Uzor, Valdini Douglace Lemofouet, Paula Chikaodinaka Anyanwu, Tassallah Abdullahi, Clemencia Siro, Idris Abdulmumin, Seid Muhie Yimam, Shamsuddeen Hassan Muhammad
arXiv:2608.29266v1 Announce Type: cross
Abstract: Researchers increasingly treat LLM survey responses as a proxy for human cultural values. This includes projecting model outputs onto instruments lik...
By An Duy Nguyen, Muhammad Aurangzeb Ahmad
The paper introduces CultureLens, a benchmark with 9,261 scenarios from 75 countries that tests how large language models (LLMs) incorporate cultural information. Experiments on Llama‑3.1‑8B, Gemma‑3‑12B, and Qwen‑3.5‑27B show that presenting a contradictory cultural norm reduces aligned answers by 32‑47 percentage points, even when the model knows the correct country. Fine‑tuning with contradictory‑norm examples improves alignment to 85‑93% under contradictory norms while only slightly affecting performance under true norms.
By Samee Arif, Furkan Danisman, Angana Borah, Honglak Lee, Dehan Kong, Lajanugen Logeswaran, Moontae Lee, Zhijing Jin, Rada Mihalcea
arXiv:2609.00565v1 Announce Type: cross
Abstract: Cultural fine-tuning has become the de facto paradigm for building culture-aware large language models (LLMs), yet existing optimization exclusively...
By Jingshen Zhang, Shaoyang Xu, Wenxuan Zhang
arXiv:2607. 08034v1 Announce Type: cross Abstract: Large language models (LLMs) are used worldwide, yet disproportionately reflect Western values, limiting their ability to represent diverse value systems.
By Dhruv Agarwal, Anya Shukla, Tanya Goyal, Aditya Vashistha
MBBQ (Multilingual Bias Benchmark for Question-answering) is a curated extension of the English BBQ dataset that includes Dutch, Spanish, and Turkish, designed to measure stereotypes across these languages while controlling for cultural differences and task accuracy. The dataset also provides a parallel control set to assess question-answering performance independently of bias. Experiments with several open-source and proprietary LLMs show that non‑English languages can exhibit greater bias than English, and cross‑lingual bias differences persist except in the most accurate models.
By Vera Neplenbroek, Arianna Bisazza, Raquel Fern\'andez
arXiv:2610.33749v1 Announce Type: new
Abstract: As machine translation systems approach human-level quality, traditional evaluation methodologies struggle to detect subtle translation errors. We crit...
By Dmitry Popov, Vladislav Negodin, Ekaterina Enikeeva, Iana Matrosova, Nikolay Karpachev, Max Ryabinin
The paper introduces CAPRI, a dataset of conversations designed to test whether large language models (LLMs) can adapt their responses to users’ cultural backgrounds. Experiments show that while LLMs can infer a user’s cultural context and recall relevant conventions, they frequently fail to apply this knowledge when generating answers unless explicitly prompted to do so. The study also finds that LLMs’ cultural adaptations improve as more cues are provided, yet their default priors are not culture‑neutral and sometimes reflect the model’s country of origin.
By Yisong Miao, Jian Zhu, Vered Shwartz